mostlygeek/llama-swap

Issues

• [Bug/Incompatibility] Continue.dev autocompletion is broken

  #32 opened a day ago
  3

• Some observations and a question about error messages

  #30 opened 4 days ago
  3

• problems unloading the model

  #28 opened 5 days ago
  3

• Add Homebrew Support for macOS

  #26 opened 8 days ago
  2

• [Bug] TTL starts counting from the beginning of a request instead of the end

  #25 opened 12 days ago
  2

• No 'Access-Control-Allow-Origin' header present on the '/v1/models' endpoint response causes the browser to block the request due to CORS policy

  #24 opened 18 days ago
  3

• Change profile model name to use a : (colon)

  #21 opened 20 days ago
  0

• [Feature] Queue requests

  #19 opened 21 days ago
  5

• List in llama.cpp readme

  #18 opened 23 days ago
  0

• [Feature] Support llama.cpp cache_prompt parameter

  #16 opened a month ago
  3

• Support more API end points.

  #12 opened a month ago
  3

• Proxy does not set content length.

  #11 opened a month ago
  5

• [enhancement] Automatically unload idle model

  #10 opened a month ago
  5

• Return errors as chat completion instead of HTTP errors

  #9 opened a day ago
  1

• Support routing to multiple backends

  #7 opened 6 days ago
  1

• Container execution

  #5 opened 2 months ago
  7

• Support the v1/embedding endpoint

  #4 opened 4 days ago
  0

• Handle crashing child processes better

  #3 opened 2 months ago
  0

• make more robust against <defunct> and crashing child processes

  #1 opened 2 months ago
  1